Explore the vast range of titles available.

Malware has emerged as a significant threat to end-users, businesses, and governments, resulting in financial losses of billions of dollars. Cybercriminals have found malware to be a lucrative business because of its evolving capabilities and ability to target diverse platforms such as PCs, mobile devices, IoT, and cloud platforms. While previous studies have explored single platform-based malware detection, no existing research has comprehensively reviewed malware detection across diverse platforms using machine learning (ML) techniques. With the rise of malware on PC or laptop devices, mobile devices and IoT systems are now being targeted, posing a significant threat to cloud environments. Therefore, a platform-based understanding of malware detection and defense mechanisms is essential for countering this evolving threat. To fill this gap and motivate further research, we present an extensive review of malware detection using ML techniques with respect to PCs, mobile devices, IoT, and cloud platforms. This paper begins with an overview of malware, including its definition, prominent types, analysis, and features. It presents a comprehensive review of machine learning-based malware detection from the recent literature, including journal articles, conference proceedings, and online resources published since 2017. This study also offers insights into the current challenges and outlines future directions for developing adaptable cross-platform malware detection techniques. This study is crucial for understanding the evolving threat landscape and for developing robust detection strategies.

The Internet of things (IoT) is the extension of Internet connectivity into physical devices and everyday objects. These IoT devices can communicate with others over the Internet and fully integrate into people’s daily life. In recent years, IoT devices still suffer from basic security vulnerabilities making them vulnerable to a variety of threats and malware, especially IoT botnets. Unlike common malware on desktop personal computer and Android, heterogeneous processor architecture issue on IoT devices brings various challenges for researchers. Many studies take advantages of well-known dynamic or static analysis for detecting and classifying botnet on IoT devices. However, almost studies yet cannot address the multi-architecture issue and consume vast computing resources for analyzing. In this paper, we propose a lightweight method for detecting IoT botnet, which based on extracting high-level features from function–call graphs, called PSI-Graph, for each executable file. This feature shows the effectiveness when dealing with the multi-architecture problem while avoiding the complexity of control flow graph analysis that is used by most of the existing methods. The experimental results show that the proposed method achieves an accuracy of 98.7%, with the dataset of 11,200 ELF files consisting of 7199 IoT botnet samples and 4001 benign samples. Additionally, a comparative study with other existing methods demonstrates that our approach delivers better outcome. Lastly, we make the source code of this work available to Github.

The intelligent manufacturing of power systems has led to many challenges. The cyber-physical system (CPS) was introduced to solve the problem of insufficient integration of equipment and systems. It brings advantages, but also risks. In the distribution network CPS, malicious attacks on the PC-PLC communication network can cause significant incidents and affect system safety. The paper discusses two challenges, of possible mutated virus attacks and multi-delay in the PC-PLC coupled network. We present for the first time a virus-mutation and multi-delay propagation model. Then, to effectively control the virus propagation in the network and minimize the cost, the paper proposes five control measures, introduces their possible control combinations, and solves the optimal control problem with the Pontryagin maximum theorem. Finally, simulations verify the optimal control strategies for all combinations. By comparing the effects of maximum control, minimum control, average control, and optimal control, the optimal control strategy has been proven to be effective.

A 2004 survey of Fortune 100 companies by the Ponemon Institute found that insiders were responsible for roughly 70 percent of reported security breaches (Reardon, 2005). BBC News, quoting another survey by data forensics from Ibas, stated that 70 percent of staff surveyed have stolen key information from the workplace, that 72 percent of these offenders had no ethical issues with helping themselves to information that would benefit them in a new job, and that 30 percent of respondents had stolen contact data when they left an employer (2004).